"A library for 3D graphics on the web - Three.js" matching MCP servers:

MCP server that gives AI agents access to current web information through web_search and fetch_url tools, using Tavily, Brave, and DuckDuckGo providers with automatic fallback.

Enables reading and sending messages in Google Messages for web through a paired Chrome tab using chromefile, with tools for status, listing conversations, reading message history, and sending texts.

Enables a locally-run LLM to search the web, fetch pages as markdown, make arbitrary HTTP requests, and optionally render pages with headless Chromium.

Gives AI agents local web search and page reading with no API keys, layering a SearXNG-backed search cache with browser-based fallbacks and returning clean page text from HTML, PDF, JSON, and archived snapshots. Fetches run in Docker alongside the search engine with SSRF protection, egress filtering, and untrusted-content marking so agents can safely retrieve live web data.

A fast web reader for AI assistants, served over MCP. It reads web pages and PDFs and returns only the passages that answer the question, not whole pages. It runs locally and keeps nothing.

Enables MCP-capable agents to perform local web research under a declared plan with session budgets, user-approved limit extensions, and guardrails for safe searching, page fetching, content extraction, and audit logging.

Provides a local MCP server for AI-powered web crawling on Windows, enabling agents to directly crawl and extract web content without requiring WSL.

Enables AI assistants to access real-time web data through search, markdown scraping, and browser automation while bypassing anti-bot protections. It provides tools for web research, e-commerce monitoring, and data extraction from across the globe.

A local MCP server providing web search, page extraction, and safe browser automation tools for Hermes, Claude Code, and other MCP clients.

MCP server for multi-engine web search and web page fetching, supporting parallel search, content extraction, and optional LLM-powered search summarization and deep search.

Enables an MCP client to read Discord servers, channels, threads, and messages, and to send messages, replies, reactions, and GIFs through an already-open Discord Web tab via a local Chrome extension and 127.0.0.1 bridge, without using a bot or the Discord HTTP API.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Enables an agent to locate embedded Flash or Java games (on live pages or in the Internet Archive), inspect whether they can run, fetch the Ruffle or CheerpJ runtime, package a self-contained static site, and verify playback in a real headless browser. Every step produces an evidence bundle so revived games can be hosted on any static host with claims backed by recorded results.

Enables compatible MCP clients to read JavaScript-rendered web pages as bounded Markdown or structured records, with URL policy and resource limits for safe, inspectable access.

Enables users to select UI elements on localhost pages and send fix requests to MCP-compatible coding agents, which retrieve the captures and edit the code, with masking of sensitive values.

Enables AI assistants to automate web interactions such as navigating pages, clicking elements, filling forms, querying the DOM, evaluating JavaScript, and inspecting network/console logs — all from a Termux terminal without Chromium, root, or proot.

Enables local web search through a SearXNG instance, returning up to eight result titles, URLs, and snippets, with optional fetching of previously returned pages under strict sandboxing and URL restrictions.

Enables AI agents to search DuckDuckGo and fetch web content with human-assisted CAPTCHA handling, designed for local use where humans can intervene when bot detection occurs.

A self-hosted MCP server that reads web pages and converts them to Markdown, with built-in web search and anti-crawl fallback using Playwright.

Enables searching CNKI's thesis database, fetching thesis details, downloading PDFs, and reading them page-by-page through HUST Library's unified digital resource access platform, with login, CAPTCHA, and rate-limit states surfaced honestly.

Converts web pages to Markdown for MCP clients like Claude, with support for single and batch reads, caching, fallback rendering, and SSRF protection.

Enables AI-powered web searches using DuckDuckGo with automatic summarization via Google's Gemini AI. Supports both summary and detailed analysis modes for search results.

MCP server that parses web pages into clean markdown via Crawl4AI's HTTP API, exposing parse_page and health-check tools with configurable proxy and timeout.

A web-fetch MCP server for LLM agents that fetches pages with an escalation ladder through different engines, raising FetchBlocked instead of returning blocked content.

An open-source MCP server providing AI agents with neural web search via Exa and tiered web fetch (Exa, local browser, Firecrawl) as a drop-in replacement for built-in web tools, preserving provenance and guarding against SSRF.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

Enables web searches through DuckDuckGo without an API key and extracts readable main content from web pages.

Enables agents to search the live web and fetch URLs as clean Markdown, returning ranked search results and paginated page content through two lightweight tools.

Wraps Xiaomi MiMo's web_search API into an MCP tool for Claude Code, enabling real-time web searches with location awareness, automatic retry, and timeout control.

Enables lightweight web search discovery and on-demand extraction of cleaned page text from supplied URLs, returning snippets, headings, links, and saved full text for longer pages.